Self-maintaining autonomous vehicle procedure

1. A method of self-maintaining an autonomous vehicle comprising: receiving models of autonomous vehicle operations from a remote analysis service, wherein the models of autonomous vehicle operations define issues and corresponding criticality levels, wherein the issues and corresponding criticality levels are continuously updated by a fleet of autonomous vehicles as the fleet of autonomous vehicles navigates; analyzing diagnostic data captured by a sensor of the autonomous vehicle; determining an operational issue with the autonomous vehicle based on the analysis of the diagnostic data, the operational issue being one of the issues defined by the models; determining a criticality level of the operational issue based on the models of autonomous vehicle operations, the criticality level being one of the corresponding criticality levels defined by the models; based on the criticality level, sending the analysis of the diagnostic data to a routing service and receiving instruction from the routing service to dynamically route the autonomous vehicle in accordance with a maintenance action; and sending one or more portions of the diagnostic data determined to be under a particular criticality level to the remote analysis service in order to update the models of autonomous vehicle operations for the fleet of autonomous vehicles; determining that, based on the diagnostic data, a physical component is restricted from a threshold movement; based on the determination, classifying the operational issue with the autonomous vehicle at a first criticality level; based on the operational issue being classified at the first criticality level, receiving instructions from the routing service to bring the autonomous vehicle to a stop; determining, by the sensor, that a passenger is within the autonomous vehicle; and sending a request for a backup service.

2. The method of claim 1 , wherein the models are continuously updated based on diagnostic data from the fleet captured dynamically as the fleet navigates.

3. The method of claim 1 , further comprising: determining that, based on the diagnostic data, a sensor calibration value is within a threshold range that exceeds an acceptable value determined as optimal for autonomous vehicle operation; based on the determination, classifying the operational issue with the autonomous vehicle at a second criticality level; and based on the operational issue being classified at the second criticality level, receiving instruction from the routing service to dynamically drive the autonomous vehicle to a maintenance facility that can service the operational issue when a passenger within the autonomous vehicle has been dropped off.

4. The method of claim 1 , further comprising: determining that the autonomous vehicle is due for preventative maintenance based diagnostic data indicating a feature of the models that is associated with a future operational issue; based on the determination, classifying the operational issue with the autonomous vehicle at a third criticality level; based on the operational issue being classified at the third criticality level, receiving confirmation from the routing service that a work order has been placed at a scheduled time with a maintenance facility that can service the operation issue; and receiving instructions from the routing service to dynamically drive the autonomous vehicle to the maintenance facility that can service the operation issue at the scheduled time.

5. A system comprising: one or more sensors of an autonomous vehicle; and a processor for executing instructions stored in memory, wherein execution of the instructions by the processor executes: receiving models of autonomous vehicle operations from a remote analysis service, wherein the models of autonomous vehicle operations define issues and corresponding criticality levels, wherein the issues and corresponding criticality levels are continuously updated by a fleet of autonomous vehicles as the fleet of autonomous vehicles navigates; analyzing diagnostic data captured by a sensor of the autonomous vehicle; determining an operational issue with the autonomous vehicle based on the analysis of the diagnostic data, the operational issue being one of the issues defined by the models; determining a criticality level of the operational issue based on the model of autonomous vehicle operations, the criticality level being one of the criticality levels defined by the models; and based on the criticality level, sending the analysis of the diagnostic data to a routing service and receiving instruction from the routing service to dynamically route the autonomous vehicle in accordance with a maintenance action; and sending one or more portions of the diagnostic data determined to be under a particular criticality level to the remote analysis service in order to update the models of autonomous vehicle operations for the fleet of autonomous vehicles; determining that, based on the diagnostic data, a physical component is restricted from a threshold movement; based on the determination, classifying the operational issue with the autonomous vehicle at a first criticality level; based on the operational issue being classified at the first criticality level, receiving instructions from the routing service to bring the autonomous vehicle to a stop; determining, by the sensor, that a passenger is within the autonomous vehicle; and sending a request for a backup service.

6. The system of claim 5 , wherein the models are continuously updated based on diagnostic data from the fleet captured dynamically as the fleet navigates.

7. The system of claim 5 , wherein execution of the instructions by the processor further executes: determining that, based on the diagnostic data, a sensor calibration value is within a threshold range that exceeds an acceptable value determined as optimal for autonomous vehicle operation; based on the determination, classifying the operational issue with the autonomous vehicle at a second criticality level; and based on the operational issue being classified at the second criticality level, receiving instruction from the routing service to dynamically drive the autonomous vehicle to a maintenance facility that can service the operational issue when a passenger within the autonomous vehicle has been dropped off.

8. The system of claim 5 , wherein execution of the instructions by the processor further executes: determining that the autonomous vehicle is due for preventative maintenance based diagnostic data indicating a feature of the model that is associated with a future operational issue; based on the determination, classifying the operational issue with the autonomous vehicle at a third criticality level; based on the operational issue being classified at the third criticality level, receiving confirmation from the routing service that a work order has been placed at a scheduled time with a maintenance facility that can service the operation issue; and receiving instructions from the routing service to dynamically drive the autonomous vehicle to the maintenance facility that can service the operation issue at the scheduled time.

9. A non-transitory computer readable medium comprising instructions, the instructions, when executed by a computing system, cause the computing system to: receive models of autonomous vehicle operations from a remote analysis service, wherein the models of autonomous vehicle operations define issues and corresponding criticality levels, wherein the issues and corresponding criticality levels are continuously updated by a fleet of autonomous vehicles as the fleet of autonomous vehicles navigates; analyze diagnostic data captured by a sensor of an autonomous vehicle; determine an operational issue with the autonomous vehicle based on the analysis of the diagnostic data, the operational issue being one of the issues defined by the models; determine a criticality level of the operational issue based on the model of autonomous vehicle operations, the criticality level being one of the corresponding criticality levels defined by the models; based on the criticality level, send the analysis of the diagnostic data to a routing service and receiving instruction from the routing service to dynamically route the autonomous vehicle in accordance with a maintenance action; and send one or more portions of the diagnostic data determined to be under a particular criticality level to the remote analysis service in order to update the models of autonomous vehicle operations for the fleet of autonomous vehicles; determine that, based on the diagnostic data, a physical component is restricted from a threshold movement; based on the determination, classify the operational issue with the autonomous vehicle at a first criticality level; based on the operational issue being classified at the first criticality level, receive instructions from the routing service to bring the autonomous vehicle to a stop; determine, by the sensor, that a passenger is within the autonomous vehicle; and send a request for a backup service.

10. The non-transitory computer readable medium of claim 9 , wherein the models are continuously updated based on diagnostic data from the fleet captured dynamically as the fleet navigates.

11. The non-transitory computer readable medium of claim 9 , the instructions further causing the computing system to: determine that, based on the diagnostic data, a sensor calibration value is within a threshold range that exceeds an acceptable value determined as optimal for autonomous vehicle operation; based on the determination, classify the operational issue with the autonomous vehicle at a second criticality level; and based on the operational issue being classified at the second criticality level, receive instruction from the routing service to dynamically drive the autonomous vehicle to a maintenance facility that can service the operational issue when a passenger within the autonomous vehicle has been dropped off.

12. The non-transitory computer readable medium of claim 9 , the instructions further causing the computing system to: determine that the autonomous vehicle is due for preventative maintenance based diagnostic data indicating a feature of the model that is associated with a future operational issue; based on the determination, classify the operational issue with the autonomous vehicle at a third criticality level; based on the operational issue being classified at the third criticality level, receive confirmation from the routing service that a work order has been placed at a scheduled time with a maintenance facility that can service the operation issue; and receive instructions from the routing service to dynamically drive the autonomous vehicle to the maintenance facility that can service the operation issue at the scheduled time.